agent-step-sequencer

---
name: agent-step-sequencer
description: Multi-step scheduler for in-depth agent requests. Detects when user needs multiple steps, suggests plan and waits for confirmation, persists state, and runs heartbeat-aware flow. Use when requests have 3+ actions, sequential dependencies, output dependencies, or high scope/risk.
metadata: {"openclaw":{"emoji":"🔗","requires":{"bins":["python3"],"env":["STEP_AGENT_CMD"]},"install":[{"id":"apt","kind":"apt","package":"python3","bins":["python3"],"label":"Install Python 3","os":["linux"]},{"id":"brew","kind":"brew","formula":"python@3","bins":["python3"],"label":"Install Python 3","os":["darwin"]}]}}
---

# Agent Step Sequencer

Multi-step scheduler for in-depth requests. Enables step-based actions with heartbeat integration—survives gateway reset mid-step.

## Core Pattern

1. **Interpret** when user request requires multiple steps
2. **Suggest** step plan, wait for confirmation
3. **Persist** state.json (with plan format)
4. **Agent invokes** `scripts/step-sequencer-check.py` immediately (no wait for heartbeat)
5. **Heartbeat** (e.g. every 5 min) also invokes the script—keeps sequencer aligned with email jobs and other heartbeat tasks

**Critical:** If gateway resets mid-step, next heartbeat reads state and resumes correctly.

---

## Plan Format

Agent builds a plan when user approves. During approval, agent asks: **Use 2-minute delay between steps?** Recommended for rate-limit–sensitive API calls. User chooses; agent sets `stepDelayMinutes` (0 or 2) in state. Each step has `title`, `instruction`, and optionally `requiredOutputs` (paths relative to workspace that must exist before the step is marked DONE):

```json
{
  "plan": {
    "steps": {
      "step-1": { "title": "Research topic X", "instruction": "Research topic X and produce a concise summary", "requiredOutputs": ["study/summary.md"] },
      "step-2": { "title": "Write paper", "instruction": "Using the summary from step 1, write a research paper..." }
    }
  },